Efficient Enhancement Algorithm based on Local Properties for Fingerprint Images

B.-G. Kim, H.-J. Kim, and D.-J. Park (Korea)


Fingerprint, Adaptive Normalisation, Gabor Filter, Enhancement


In this paper, an improved algorithm for enhancement of fingerprint images is proposed on the basis of image normalization and the Gabor filter. The adaptive normalization based on block processing is suggested for improvement of fingerprint images. An input image is partitioned into sub-blocks with the size of K × L at first and the region of interest (ROI) of the fingerprint image is acquired. The parameters for the image normalization are adaptively determined according to the statistics of each block. By utilizing these parameters, the block image is normalized for the next process. A new technique for selection of two important parameters of the Gabor filter is devised. These parameters are the ridge direction and the ridge frequency. The ridge direction of a block image is determined by a probabilistic approach unlike other works. With this ridge direction, the ridge frequency is selected by utilizing the directional projection and its frequency response. The pro posed algorithms are tested with the NIST fingerprint images and show significant improvement in the experiments.

Important Links:

Go Back